Skip to main content
POST
Create a new evaluation to assess a dataset using one or more evaluators. The evaluation runs asynchronously, use the Get Evaluation endpoint to check status.

Authentication

string
required
Bearer token with write scope. Example: Bearer gr_live_xxxxxxxx

Request Body

string
required
A descriptive name for this evaluation run. Useful for identifying evaluations in the dashboard.
string
required
The project ID to run this evaluation in. Must be a valid project you have access to.
string
required
The dataset ID containing samples to evaluate. All samples in the dataset will be processed.
array
required
List of evaluator configurations to run against each sample.
object
Arbitrary key-value pairs to attach to this evaluation for filtering and organization.
boolean
default:"true"
Whether to run the evaluation asynchronously.
Evaluator TypesSee the Evaluators Reference for a complete list of built-in evaluator types and their configuration options.

Response

string
Unique identifier for the evaluation. Example: eval_def456
string
Always evaluation
string
The name provided for this evaluation
string
The project ID this evaluation belongs to
string
The dataset ID being evaluated
string
Current status: pending, running, completed, failed, cancelled
array
The evaluator configurations for this evaluation
object
string
ISO 8601 timestamp when the evaluation was created
string
ISO 8601 timestamp when processing started (null if pending)
string
ISO 8601 timestamp when processing completed (null if not finished)
object
Custom metadata attached to this evaluation

Get Evaluation

Retrieve evaluation details and results

List Evaluations

List all evaluations in a project

Get Status

Check evaluation progress